© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21421
    Prev
    Next
    INDEX
    Explanations

    to be or not to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     μετά
    0.42
     базу
    0.42
     именем
    0.41
     "`
    0.40
    Launch
    0.40
     после
    0.40
    грани
    0.39
     pathway
    0.39
    嶆
    0.39
     тести
    0.39
    POSITIVE LOGITS
     española
    0.56
     நிர்வாகிகள்
    0.50
     Españ
    0.49
     साध
    0.47
     पढ़े
    0.47
     españoles
    0.46
     ô
    0.44
     gehö
    0.44
     italiana
    0.44
    ņas
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.